Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to personal beliefs and actions

    oai_token-act-pair · gpt-3.5-turbo

    negations or expressions of doubt and uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ð
    -0.73
    SPONSORED
    -0.72
    ire
    -0.63
    bush
    -0.62
    ê
    -0.62
    tains
    -0.61
    donald
    -0.61
    alist
    -0.61
    "[
    -0.61
    Hur
    -0.60
    POSITIVE LOGITS
     however
    0.94
     ital
    0.76
     therefore
    0.75
     moreover
    0.74
     meanwhile
    0.69
     furthermore
    0.69
     though
    0.66
     certainly
    0.64
     defin
    0.63
    ĸļ
    0.62
    Act Density 1.043%

    No Known Activations